© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 281
    Prev
    Next
    INDEX
    Explanations

    references to ordinal numbers, particularly "fourth" and "fifth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    -0.69
    er
    -0.68
     Ges
    -0.67
    gdala
    -0.66
    apos
    -0.63
    aluz
    -0.61
     Cannes
    -0.60
     Meridian
    -0.59
    skis
    -0.57
    erai
    -0.57
    POSITIVE LOGITS
     third
    1.62
     fifth
    1.58
     THIRD
    1.57
     fourth
    1.56
    Third
    1.55
    THIRD
    1.54
     seventh
    1.52
     Third
    1.52
     sixth
    1.51
    Fifth
    1.50
    Activations Density 0.087%

    No Known Activations